caveman-review

Generates terse one-line code review comments for pull request diffs.

1|Updated Jun 6, 2026
One-click install
npx skills add https://github.com/karuhun-developer/ecommerce --skill caveman-review-karuhun-developer
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: caveman-review
Source: https://github.com/karuhun-developer/ecommerce/tree/main/.ai/skills/caveman-review
Command: npx skills add https://github.com/karuhun-developer/ecommerce --skill caveman-review-karuhun-developer

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? Code review feedback is often buried in verbose, hedged prose that obscures the actionable point. This Skill compresses PR review comments into single-line findings with location, problem, and fix, cutting noise while preserving signal. ## Core Features & Use Cases - One-Line Findings: Each comment follows the format L<line>: <problem>. <fix>. with exact line numbers and symbol names in backticks. - Severity Prefixes: Optional tags classify findings as bug, risk, nit, or question so authors can triage feedback quickly. - Auto-Clarity Mode: Automatically expands to full paragraphs for security findings, architectural disagreements, or onboarding contexts where rationale matters. - Use Case: A reviewer pastes a multi-file diff and receives paste-ready comments like L42: bug: user can be null after .find(). Add guard before .email. instead of writing paragraph-length explanations. ## Quick Start Review this pull request diff and give me terse one-line comments for each finding.

Frequently Asked Questions about caveman-review

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I write concise code review comments?▼

Use the format L<line>: <problem>. <fix>. with exact line numbers and symbol names in backticks. Drop hedging phrases like "I noticed" or "you might want to consider" and state the concrete fix directly.

How to categorize severity in pull request feedback?▼

Prefix each finding with a severity tag: bug for broken behavior, risk for fragile code like missing null checks, nit for style issues, and q for genuine questions. This lets authors triage feedback by impact.

When should code review comments be detailed instead of terse?▼

Security findings, architectural disagreements, and reviews for new team members need full explanations with rationale. Terse one-liners work for routine bugs, risks, and style nits where the fix is self-evident.

Does this skill write the code fixes it suggests?▼

No. It only outputs review comments ready to paste into a PR. It does not write code fixes, approve or request changes on the review, or run linters against the diff.

Can I turn off terse review mode mid-session?▼

Yes. Saying "stop caveman-review" or "normal mode" reverts to verbose review style. The skill also auto-expands for security and architectural findings without being asked.